Methods

The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning NeurIPS 2022 The Importance of Non-Markovianity in Maximum State Entropy Exploration ICML 2022 The Nature of Temporal Difference Errors in Multi-step Distributional Reinforcement Learning NeurIPS 2022 Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods AAAI 2022 The Phenomenon of Policy Churn NeurIPS 2022 The Pitfalls of Regularization in Off-Policy TD Learning NeurIPS 2022 The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces ICML 2022 The Primacy Bias in Deep Reinforcement Learning ICML 2022 The Role of Baselines in Policy Gradient Optimization NeurIPS 2022 The Role of Pretrained Representations for the OOD Generalization of RL Agents ICLR 2022 The State of Sparse Training in Deep Reinforcement Learning ICML 2022 The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games NeurIPS 2022 “Think Before You Speak”: Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs IJCAI 2022 Thompson Sampling Achieves Õ(√T) Regret in Linear Quadratic Control COLT 2022 Thompson Sampling Efficiently Learns to Control Diffusion Processes NeurIPS 2022 Tianshou: A Highly Modularized Deep Reinforcement Learning Library JMLR 2022 Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret NeurIPS 2022 TinyLight: Adaptive Traffic Signal Control on Devices with Extremely Limited Resources IJCAI 2022 TopKG: Target-oriented Dialog via Global Planning on Knowledge Graph COLING 2022 Topological Experience Replay ICLR 2022 Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning ICML 2022 Toward Policy Explanations for Multi-Agent Reinforcement Learning IJCAI 2022 Towards an Understanding of Default Policies in Multitask Policy Optimization AISTATS 2022 Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble IJCAI 2022 Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods ICML 2022